Triple
T13681606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feeding of the five thousand |
E328015
|
entity |
| Predicate | hasAudienceInNarrative |
P38554
|
FINISHED |
| Object | Jewish crowd |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Jewish crowd | Statement: [Feeding of the five thousand, hasAudienceInNarrative, Jewish crowd]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAudienceInNarrative Context triple: [Feeding of the five thousand, hasAudienceInNarrative, Jewish crowd]
-
A.
hasAudience
Indicates that an entity is intended to be received, viewed, or engaged with by a particular group of people.
-
B.
hasPartInNarrative
chosen
Indicates that one entity plays a role or participates as a component within the storyline or structure of another narrative entity.
-
C.
hasNarrativeRole
Indicates that an entity participates in a narrative with a specific functional role (e.g., protagonist, antagonist, narrator) relative to the story.
-
D.
hasAliasInNarrative
Indicates that an entity is referred to by an alternative name or alias within a specific narrative or story context.
-
E.
hasTypeInNarrative
Indicates that an entity is assigned a specific type or role within the context of a particular narrative.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8076f1fa8819094664a59b55010df |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc66e75188190a9e82fdc5eb26513 |
completed | April 12, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69dbbe8d8d0881908d6e89954f44eed4 |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 9:53 p.m.